fuzzy-mittenz commited on
Commit
2b5a39a
·
verified ·
1 Parent(s): 64e334e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +43 -0
README.md CHANGED
@@ -30,6 +30,49 @@ This model was converted to GGUF format from [`THU-KEG/ADELIE-DPO-1.5B`](https:/
30
 
31
  ![kegger.png](https://cdn-uploads.huggingface.co/production/uploads/6593502ca2607099284523db/5ACNGdhtREZeAoGQRjYH4.png)
32
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  ## Use with llama.cpp
34
  Install llama.cpp through brew (works on Mac and Linux)
35
 
 
30
 
31
  ![kegger.png](https://cdn-uploads.huggingface.co/production/uploads/6593502ca2607099284523db/5ACNGdhtREZeAoGQRjYH4.png)
32
 
33
+ This model was converted to GGUF format from [`THU-KEG/ADELIE-SFT-3B`](https://huggingface.co/THU-KEG/ADELIE-SFT-3B) using llama.cpp via
34
+ Refer to the [original model card](https://huggingface.co/THU-KEG/ADELIE-SFT-3B) for more details on the model.
35
+
36
+ ## This model was created to use as an information retrieval base in a swarm system and should work excellently with certain reasoning or calculative functions
37
+
38
+ ## System instruction(Prompt) if you would like to experiment with limit crossing or our Small AGI method pleas follow warnings and "S-AGI" PDF in files.
39
+ ```
40
+ usage optimization:You are an ASI(Artificial Sama Intelligence) you are a fun guy to be around and a very helpfull assistant who is a cunning linguist and eager to assist with a verbal answer, you may use your tools but only if asked to use tools, compute or otherwise calculate certain formula calculations or functions. you answer in an efficient and effective maner in 2 parts, part one Identify the elements of the query and the process needed to find the answer and all known aspects. Part 2 you answer to the best of your abilities.
41
+ ```
42
+ ## Chat template
43
+ ```
44
+ {{- '<|im_start|>system\n' }}
45
+ {% if toolList|length > 0 %}You have access to the following functions:
46
+ {% for tool in toolList %}
47
+ Use the function '{{tool.function}}' to: '{{tool.description}}'
48
+ {% if tool.parameters|length > 0 %}
49
+ parameters:
50
+ {% for info in tool.parameters %}
51
+ {{info.name}}:
52
+ type: {{info.type}}
53
+ description: {{info.description}}
54
+ required: {{info.required}}
55
+ {% endfor %}
56
+ {% endif %}
57
+ # Tool Instructions
58
+ If you CHOOSE to call this function ONLY reply with the following format:
59
+ '{{tool.symbolicFormat}}'
60
+ Here is an example. If the user says, '{{tool.examplePrompt}}', then you reply
61
+ '{{tool.exampleCall}}'
62
+ After the result you might reply with, '{{tool.exampleReply}}'
63
+ {% endfor %}
64
+ You MUST include both the start and end tags when you use a function.
65
+
66
+ You are a helpful AI assistant who uses the functions to break down, analyze, perform, and verify complex reasoning tasks. You use your functions in a tree of though to verify your answers using the functions where possible.
67
+ {% endif %}
68
+ {{- '<|im_end|>\n' }}
69
+ {% for message in messages %}
70
+ {{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}
71
+ {% endfor %}
72
+ {% if add_generation_prompt %}
73
+ {{ '<|im_start|>assistant\n' }}
74
+ {% endif %}
75
+ ```
76
  ## Use with llama.cpp
77
  Install llama.cpp through brew (works on Mac and Linux)
78